search for: nv50loweringpressa

...543,7 @@ private: bool handleTXB(TexInstruction *); // I really bool handleTXL(TexInstruction *); // hate bool handleTXD(TexInstruction *); // these 3 + bool handleTXLQ(TexInstruction *); bool handleCALL(Instruction *); bool handlePRECONT(Instruction *); @@ -856,6 +857,26 @@ NV50LoweringPreSSA::handleTXD(TexInstruction *i) } bool +NV50LoweringPreSSA::handleTXLQ(TexInstruction *i) +{ + handleTEX(i); + bld.setPosition(i, true); + + /* The returned values are not quite what we want: + * (a) convert from s32 to f32 + * (b) multiply by 1/256 + */ + for (int def = 0; def &...

...drivers/nouveau/codegen/nv50_ir_lowering_nv50.cpp b/src/gallium/drivers/nouveau/codegen/nv50_ir_lowering_nv50.cpp index 984a8ca..0908447 100644 --- a/src/gallium/drivers/nouveau/codegen/nv50_ir_lowering_nv50.cpp +++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_lowering_nv50.cpp @@ -664,7 +664,7 @@ NV50LoweringPreSSA::handleTEX(TexInstruction *i) bld.mkOp2(OP_MIN, TYPE_U32, src, src, bld.loadImm(NULL, 511)); i->setSrc(arg - 1, src); } - if (i->tex.target.isCube()) { + if (i->tex.target.isCube() && i->srcCount() > 4) { std::vector<Value *&g...

OK, so there's a bunch of stuff in here. The geometry stuff is based on the work started by Bryan Cain and Christoph Bumiller. Patches 01-12: Add support for geometry shaders and fix related issues Patches 13-14: Make it possible for fb clears to operate on texture attachments with an explicit layer set (as is allowed in gl 3.2). Patches 15-17: Make ARB_texture_multisample work

...s/nouveau/codegen/nv50_ir_lowering_nv50.cpp b/src/gallium/drivers/nouveau/codegen/nv50_ir_lowering_nv50.cpp index eafc0a7..63db1d7 100644 --- a/src/gallium/drivers/nouveau/codegen/nv50_ir_lowering_nv50.cpp +++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_lowering_nv50.cpp @@ -591,6 +591,10 @@ void NV50LoweringPreSSA::loadTexMsInfo(uint32_t off, Value **ms, Value *tmp = new_LValue(func, FILE_GPR); uint8_t b = prog->driver->io.resInfoCBSlot; off += prog->driver->io.suInfoBase; + if (prog->getType() > Program::TYPE_VERTEX) + off += 16 * 2 * 4; + if (prog->getType() > P...

...ivers/nouveau/codegen/nv50_ir_lowering_nv50.cpp b/src/gallium/drivers/nouveau/codegen/nv50_ir_lowering_nv50.cpp index caaf09f..07f3a21 100644 --- a/src/gallium/drivers/nouveau/codegen/nv50_ir_lowering_nv50.cpp +++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_lowering_nv50.cpp @@ -575,14 +575,16 @@ NV50LoweringPreSSA::handleTEX(TexInstruction *i) if (i->op == OP_TXB || i->op == OP_TXL) i->swapSources(dref, lod); - // array index must be converted to u32 if (i->tex.target.isArray()) { - Value *layer = i->getSrc(arg - 1); - LValue *src = new_LValue(func, FILE_GPR)...

This can only happen with texture(samplerCubeShadow, bias), where the compare will be in the first argument. Signed-off-by: Ilia Mirkin <imirkin at alum.mit.edu> Cc: <mesa-stable at lists.freedesktop.org> --- src/gallium/drivers/nouveau/codegen/nv50_ir_from_tgsi.cpp | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git

...drivers/nouveau/codegen/nv50_ir_lowering_nv50.cpp b/src/gallium/drivers/nouveau/codegen/nv50_ir_lowering_nv50.cpp index e283424..0d7612e 100644 --- a/src/gallium/drivers/nouveau/codegen/nv50_ir_lowering_nv50.cpp +++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_lowering_nv50.cpp @@ -772,7 +772,8 @@ NV50LoweringPreSSA::handleTEX(TexInstruction *i) if (i->tex.useOffsets) { for (int c = 0; c < 3; ++c) { ImmediateValue val; - assert(i->offset[0][c].getImmediate(val)); + if (!i->offset[0][c].getImmediate(val)) + assert(!"non-immediate offset");...

...ivers/nouveau/codegen/nv50_ir_lowering_nv50.cpp b/src/gallium/drivers/nouveau/codegen/nv50_ir_lowering_nv50.cpp index 0d7612e..1ad0860 100644 --- a/src/gallium/drivers/nouveau/codegen/nv50_ir_lowering_nv50.cpp +++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_lowering_nv50.cpp @@ -1094,8 +1094,9 @@ NV50LoweringPreSSA::handleRDSV(Instruction *i) case SV_FACE: bld.mkInterp(NV50_IR_INTERP_FLAT, def, addr, NULL); if (i->dType == TYPE_F32) { - bld.mkOp2(OP_AND, TYPE_U32, def, def, bld.mkImm(0x80000000)); - bld.mkOp2(OP_XOR, TYPE_U32, def, def, bld.mkImm(0xbf800000)); + bl...

...NV50LegalizeSSA::visit(BasicBlock *bb) case OP_MUL: handleMUL(insn); break; + case OP_RCP: + case OP_RSQ: + if (insn->dType == TYPE_F64) + handleDRCPRSQ(insn); + break; default: break; } @@ -1162,7 +1257,7 @@ NV50LoweringPreSSA::handleDIV(Instruction *i) bool NV50LoweringPreSSA::handleSQRT(Instruction *i) { - Instruction *rsq = bld.mkOp1(OP_RSQ, TYPE_F32, + Instruction *rsq = bld.mkOp1(OP_RSQ, i->dType, bld.getSSA(), i->getSrc(0)); i->op = OP_MUL; i->setSrc(1, rs...

https://bugs.freedesktop.org/show_bug.cgi?id=78161 Priority: medium Bug ID: 78161 Assignee: nouveau at lists.freedesktop.org Summary: [NV96] Artifacts in output of fragment program containing not unrolled loops with conditional break Severity: normal Classification: Unclassified OS: Linux (All)

I went through the gallium-nine tree and picked out nouveau patches that are general bug-fixes. The first bunch I'd like to also get into 10.2. I've reviewed all of them and they make sense to me, but sending them out for public review as well in case there are any objections. Unless I hear objections, I'd like to push this by Friday. Christoph Bumiller (11): nv50,nvc0: always pull